KuralHub lists 2 speech emotion recognition datasets for Czech. Each entry below gives the emotion labels, size, recording setup, licence, where to get it and how to cite it.
Language family
Indo-European (Slavic)
ISO code
cs
Spoken mainly in
Czech Republic, European Union, Austria, Bosnia and Herzegovina, Croatia, Poland, Romania, Slovakia
The Czech Database of Speech Emotions was developed to support research in speech emotion recognition for the Czech language. It comprises short audio recordings extracted from broadcasts of three radio stations and one television channel. The dataset covers four emotional states: joy, anger, sadness, and neutral. The recordings were manually selected to ensure clear representation of each emotion.
Citation
@inproceedings{uhrin2014design,
title={Design and implementation of Czech database of speech emotions},
author={Uhrin, D and Partila, P and Voznak, M and Chmelikova, Z and Hlozak, M and Orcik, L},
booktitle={2014 22nd Telecommunications Forum Telfor (TELFOR)},
pages={529--532},
year={2014},
organization={IEEE}
}
The Slavic Call Center Emotional Speech Corpus is designed for automatic recognition of emotional expressions from spontaneous Slavic speech. The corpus is built from speech extracts obtained from real call center recordings involving four Slavic languages: Czech, Polish, Russian, and Slovak. It encompasses five different emotional states: anger, happiness, sadness, surprise, and neutral. The dataset captures the natural emotional expressions found in customer service interactions, providing valuable data for research in emotion recognition systems.
Citation
@inproceedings{atassi2012emotion,
title={Emotion recognition from spontaneous Slavic speech},
author={Atassi, Hicham and Sm{\'e}kal, Zdenek and Esposito, Anna},
booktitle={2012 IEEE 3rd international conference on cognitive infocommunications (CogInfoCom)},
pages={389--394},
year={2012},
organization={IEEE}
}
Know another Czech speech emotion dataset, or a newer version of one listed here? Suggest it or open a pull request.
This page is generated from datasets/Czech/ in the KuralHub repository.
If you use a dataset, cite its authors. If KuralHub helped you find it, please also cite the KuralHub paper.