Emotional Voice Messages (EMOVOME) database: emotion recognition in spontaneous voice messages

TL;DR

The EMOVOME database offers a large, naturalistic Spanish speech dataset with emotion labels, enabling improved emotion recognition models in real-world voice messages, with baseline results provided.

Contribution

This paper introduces EMOVOME, a novel spontaneous speech dataset with emotion annotations, and establishes baseline emotion recognition models using speech and text.

Findings

Speech-based models achieved around 49% accuracy for valence.

Text-based models achieved over 61% accuracy for valence.

The dataset provides a valuable resource for emotion recognition research in natural settings.

Abstract

Emotional Voice Messages (EMOVOME) is a spontaneous speech dataset containing 999 audio messages from real conversations on a messaging app from 100 Spanish speakers, gender balanced. Voice messages were produced in-the-wild conditions before participants were recruited, avoiding any conscious bias due to laboratory environment. Audios were labeled in valence and arousal dimensions by three non-experts and two experts, which were then combined to obtain a final label per dimension. The experts also provided an extra label corresponding to seven emotion categories. To set a baseline for future investigations using EMOVOME, we implemented emotion recognition models using both speech and audio transcriptions. For speech, we used the standard eGeMAPS feature set and support vector machines, obtaining 49.27% and 44.71% unweighted accuracy for valence and arousal respectively. For text, we fine-tuned a multilingual BERT model and achieved 61.15% and 47.43% unweighted accuracy for valence and arousal respectively. This database will significantly contribute to research on emotion recognition in the wild, while also providing a unique natural and freely accessible resource for Spanish.