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 three 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.

{"references": ["Burkhardt et al: (2022): SyntAct: A Synthesized Database of Basic Emotions"]}

Creation framework available at https://github.com/felixbur/syntAct/