Non-Parallel Training Approach for Emotional Voice Conversion Using CycleGAN

Mohamed Elsayed, Sama Hadhoud, Alaa Elsetohy, Menna Osman, Walid Gomaa, Walid Gomaa

2023

Abstract

The focus of this research is proposing a nonparallel emotional voice conversion for Egyptian Arabic speech. This method aims to change emotion-related features of a speech signal without changing its lexical content or speaker identity. We relied on the assumption that any speech signal can be divided into content and style code and the conversion between different emotion domains is done by combining the target style code with the content code of the input speech signal. We evaluated the model using an Egyptian Arabic dataset covering two emotion domains and the conversion results were successful depending on a survey conducted on random people. Our purpose is to produce a state-of-the-art pre-trained model as it will be an unprecedented model in the Egyptian Arabic language as far as we are concerned.

Paper Citation

in Harvard Style

Elsayed M., Hadhoud S., Elsetohy A., Osman M. and Gomaa W. (2023). Non-Parallel Training Approach for Emotional Voice Conversion Using CycleGAN. In Proceedings of the 20th International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO; ISBN 978-989-758-670-5, SciTePress, pages 17-24. DOI: 10.5220/0012156000003543

in Bibtex Style

@conference{icinco23,
author={Mohamed Elsayed and Sama Hadhoud and Alaa Elsetohy and Menna Osman and Walid Gomaa},
title={Non-Parallel Training Approach for Emotional Voice Conversion Using CycleGAN},
booktitle={Proceedings of the 20th International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO},
year={2023},
pages={17-24},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012156000003543},
isbn={978-989-758-670-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 20th International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO
TI - Non-Parallel Training Approach for Emotional Voice Conversion Using CycleGAN
SN - 978-989-758-670-5
AU - Elsayed M.
AU - Hadhoud S.
AU - Elsetohy A.
AU - Osman M.
AU - Gomaa W.
PY - 2023
SP - 17
EP - 24
DO - 10.5220/0012156000003543
PB - SciTePress