Original title: Difuzní neurální model pro rekonstrukci poškozených audio signálů
Translated title: Diffusion neural model for reconstruction of corrupted audio signals
Authors: Niková, Kristína ; Švento, Michal (referee) ; Mokrý, Ondřej (advisor)
Document type: Bachelor's theses
Year: 2024
Language: slo
Publisher: Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií
Abstract: [slo] [eng]
Táto bakalárska práca sa venuje návrhu difúzneho neurónového modelu pre rekonštrukciu audio signálov poškodených výpadkom vzorkou. Práca skúma princíp difúznych neurónových sieti a ich schopnosť rekonštruovať poškodené audio signály. This bachelor’s thesis is dedicated to the design of a diffusion neural network model for the reconstruction of audio signals damaged by audio inpainting. The work explores the principle of diffusion neural networks and their ability to reconstruct damaged audio signals.
Keywords: audio inpainting.; damaged audio signal; data restoration; Diffusion neural networks; machine learning; neural models; signal reconstruction

Institution: Brno University of Technology (web)
Document availability information: Fulltext is available in the Brno University of Technology Digital Library.
Original record: https://hdl.handle.net/11012/247369

Permalink: http://www.nusl.cz/ntk/nusl-619304


The record appears in these collections:
Universities and colleges > Public universities > Brno University of Technology
Academic theses (ETDs) > Bachelor's theses