The Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS): A dynamic, multimodal set of facial and vocal expressions in North American English
Аудиовизуальная база данных эмоциональной речи и пения Райерсонского университета (RAVDESS): динамический мультимодальный набор мимических и вокальных выражений на североамериканском английском языке
2018-05-16
SCID: 54.1/ssqtt3jh
Discuss with AI
North American EnglishRAVDESS databaseemotional speech and songemotional validitymultimodal facial and vocal expressions
Figures from the paper
Abstract (AI)
The RAVDESS is a validated multimodal database of emotional speech and song. The database is gender balanced consisting of 24 professional actors, vocalizing lexically-matched statements in a neutral North American accent. Speech includes calm, happy, sad, angry, fearful, surprise, and disgust expressions, and song contains calm, happy, sad, angry, and fearful emotions. Each expression is produced at two levels of emotional intensity, with an additional neutral expression. All conditions are available in face-and-voice, face-only, and voice-only formats. The set of 7356 recordings were each rated 10 times on emotional validity, intensity, and genuineness. Ratings were provided by 247 individuals who were characteristic of untrained research participants from North America. A further set of 72 participants provided test-retest data. High levels of emotional validity and test-retest intrarater reliability were reported. Corrected accuracy and composite "goodness" measures are presented to assist researchers in the selection of stimuli. All recordings are made freely available under a Creative Commons license and can be downloaded at https://doi.org/10.5281/zenodo.1188976.
Key Findings
1
Corrected accuracy and composite goodness measures are provided, and all recordings are freely available under a Creative Commons license.
2
It comprises 7,356 recordings rated ten times for emotional validity, intensity, and genuineness by 247 North American participants.
3
RAVDESS is a validated, gender-balanced multimodal database containing emotional speech and song from 24 professional actors using lexically matched North American English statements.
4
The database covers multiple emotions, two emotional-intensity levels, and neutral expressions, with recordings available in face-and-voice, face-only, and voice-only formats.
5
The stimuli demonstrated high emotional validity and test-retest intrarater reliability, supported by additional data from 72 participants.
Research Object
The Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS) — a validated multimodal database of facial and vocal emotional expressions in North American English
Research Subject
The emotional validity, intensity, genuineness, and test–retest reliability of facial and vocal expressions across emotions, modalities, and intensity levels
Publication Details
Publication Date
2018-05-16
Journal
Publisher
ISSN
Cited by
1955
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest