SyntAct: A Synthesized Database of Basic Emotions

Felix Burkhardt, Florian Eyben, Björn Schuller


Abstract
Speech emotion recognition is in the focus of research since several decades and has many applications. One problem is sparse data for supervised learning. One way to tackle this problem is the synthesis of data with emotion simulating speech synthesis approaches. We present a synthesized database of five basic emotions and neutral expression based on rule based manipulation for a diphone synthesizer which we release to the public. The database has been validated in several machine learning experiments as a training set to detect emotional expression from natural speech data. The scripts to generate such a database have been made open source and could be used to aid speech emotion recognition for a low resourced language, as MBROLA supports 35 languages
Anthology ID:
2022.dclrl-1.1
Volume:
Proceedings of the Workshop on Dataset Creation for Lower-Resourced Languages within the 13th Language Resources and Evaluation Conference
Month:
June
Year:
2022
Address:
Marseille, France
Editors:
Jonne Sälevä, Constantine Lignos
Venue:
DCLRL
SIG:
Publisher:
European Language Resources Association
Note:
Pages:
1–9
Language:
URL:
https://aclanthology.org/2022.dclrl-1.1
DOI:
Bibkey:
Cite (ACL):
Felix Burkhardt, Florian Eyben, and Björn Schuller. 2022. SyntAct: A Synthesized Database of Basic Emotions. In Proceedings of the Workshop on Dataset Creation for Lower-Resourced Languages within the 13th Language Resources and Evaluation Conference, pages 1–9, Marseille, France. European Language Resources Association.
Cite (Informal):
SyntAct: A Synthesized Database of Basic Emotions (Burkhardt et al., DCLRL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.dclrl-1.1.pdf