The Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS): A dynamic, multimodal set of facial and vocal expressions in North American English.

Steven R Livingstone,Frank A Russo,Joseph Najbauer

doi:10.1371/journal.pone.0196391

Abstract

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.

Highlights

The study of emotion has advanced rapidly over the last decade, driven by low-cost smart technologies and broad interest from researchers in neuroscience, psychology, psychiatry, audiology, and computer science
We developed the RAVDESS, a large validated set of audiovisual speech and song in North American English
The RAVDESS has several important features that lend itself for use by scientists, engineers, and clinicians: it is large in number, it contains visual and auditory depictions of spoken and sung expressions, it consists of professional actors from North America, it has a variety of emotional expressions at two levels of emotional intensity, and it is made freely available under a Creative Commons non-commercial license

Summary

Introduction

The study of emotion has advanced rapidly over the last decade, driven by low-cost smart technologies and broad interest from researchers in neuroscience, psychology, psychiatry, audiology, and computer science. Integral to these studies is the availability of validated and reliable expressions of emotion. To meet these needs, a growing number of emotion stimulus sets have become available. There are few validated sets of sung emotional expression To address these needs, we developed the RAVDESS, a large validated set of audiovisual speech and song in North American English. This paper describes the creation of the RAVDESS, and reports validity and reliability data based on ratings from healthy, adult participants

Methods

Results

Discussion

Conclusion