Thesis Details

Robustní odšumování a dereverberace audia

Bachelor's Thesis Student: Košina Simon Academic Year: 2021/2022 Supervisor: Szőke Igor, Ing., Ph.D.
English title
Robust Audio Dereverberation and Denoising
Language
Czech
Abstract

The goal of this thesis was to create a speech enhancement and dereverberation model for audio recordings coming from aircraft VHF communication. First, the thesis covers some theoretical grounds of machine learning and types of neural networks commonly used in such scenarios. Following is a description of the used framework, datasets and the implementation itself. Last chapters are focused on the performed experiments and their evaluation. At the end we talk about the future work that can be done in order to further improve the achieved results.

Keywords

speech enhancement, machine learning, VHF communication, GAN, generative adversarial network, SpeechBrain

Department
Degree Programme
Files
Status
defended, grade A
Date
15 June 2022
Reviewer
Committee
Černocký Jan, prof. Dr. Ing. (DCGM FIT BUT), předseda
Bartík Vladimír, Ing., Ph.D. (DIFS FIT BUT), člen
Češka Milan, doc. RNDr., Ph.D. (DITS FIT BUT), člen
Jaroš Jiří, doc. Ing., Ph.D. (DCSY FIT BUT), člen
Orság Filip, Ing., Ph.D. (DITS FIT BUT), člen
Citation
KOŠINA, Simon. Robustní odšumování a dereverberace audia. Brno, 2022. Bachelor's Thesis. Brno University of Technology, Faculty of Information Technology. 2022-06-15. Supervised by Szőke Igor. Available from: https://www.fit.vut.cz/study/thesis/21381/
BibTeX
@bachelorsthesis{FITBT21381,
    author = "Simon Ko\v{s}ina",
    type = "Bachelor's thesis",
    title = "Robustn\'{i} od\v{s}umov\'{a}n\'{i} a dereverberace audia",
    school = "Brno University of Technology, Faculty of Information Technology",
    year = 2022,
    location = "Brno, CZ",
    language = "czech",
    url = "https://www.fit.vut.cz/study/thesis/21381/"
}
Back to top