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

TLDR

RAVDESS is a validated multimodal database of emotional speech and song. The database comprises 24 professional actors who delivered lexically matched statements in a neutral North American accent, producing 7 speech and 5 song emotions at two intensity levels plus neutral, with 7,356 recordings available in face‑and‑voice, face‑only, and voice‑only formats, each rated 10 times by 247 untrained participants and supplemented by test‑retest data from 72 participants. The recordings exhibit high emotional validity and test‑retest intrarater reliability, and the authors provide corrected accuracy and composite goodness metrics to aid stimulus selection, with all files freely available under a Creative Commons license at https://doi.org/10.5281/zenodo.1188976.

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.