About TwineTwine NetworkContact
Audio-visual emotion recognition
These expressions are produced at two levels of emotional intensities (regular and strong) except for the neutral emotion that only contains regular intensity.
Files
100
Size
Format
wav
This Audio-Visual Database of Emotional Speech contains 100 recordings with acted-emotional content. These files are divided into three modalities (full AV, video-only, and audio-only) and two vocal channels (speech and song). Each file contains a single actor representing an emotion that could be one of the eight following categories: calm, neutral, happy, sad, angry, fearful, surprised, and disgusted.
Dataset Technical Specification
Number of files:
100
Total dataset size:
Duration:
Format:
wav
Sample rate:
Resolution:
Dataset Demographics
Country:
Worldwide
Gender:
M/F 50-50%
Age:
18-55
Number of participants:
50
