Thesis Details

Conversion of Whispered to Normal Voice

Bachelor's Thesis Student: Gajda Richard Academic Year: 2020/2021 Supervisor: Brukner Jan, Ing.
Czech title
Konverze šeptané řeči na normální
Language
English
Abstract

The aim of this thesis is to develop a working program, that converts whispered speech input into voice using vocal excitation prediction, which is obtained from a neural network. The work is based on a study from Indian Institute of Science in Bengalore, India. The approach to the solution is the following: to acquire a dataset from training speakers, to implement the speech parameterization using the WORLD vocoder, to implement and train the neural networks, to experiment, to evaluate the results and, finally,  to propose future applications and improvements.

Keywords

Speech synthesis, whispered speech, WORLD, BLSTM, conversion.

Department
Department of Computer Graphics and Multimedia FIT BUT
Degree Programme
Information Technology
Files
Status
defended, grade C
Date
16 June 2021
Reviewer
Černocký Jan, prof. Dr. Ing.
Committee
Černocký Jan, prof. Dr. Ing. (DCGM FIT BUT), předseda
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
Rychlý Marek, RNDr., Ph.D. (DIFS FIT BUT), člen
Citation
GAJDA, Richard. Conversion of Whispered to Normal Voice. Brno, 2021. Bachelor's Thesis. Brno University of Technology, Faculty of Information Technology. 2021-06-16. Supervised by Brukner Jan. Available from: https://www.fit.vut.cz/study/thesis/22505/
BibTeX 
@bachelorsthesis{FITBT22505,
    author = "Richard Gajda",
    type = "Bachelor's thesis",
    title = "Conversion of Whispered to Normal Voice",
    school = "Brno University of Technology, Faculty of Information Technology",
    year = 2021,
    location = "Brno, CZ",
    language = "english",
    url = "https://www.fit.vut.cz/study/thesis/22505/"
}

Theses

Back to top