Dawn of the Transformer Era in Speech Emotion Recognition: Closing the Valence Gap

Published in IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023

Our seminal publication on the use of transformers for speech emotion recognition. Contains insights on fairness, robustness, complementarity between text & audio, and generalization. Associated with the publication of a model to predict arousal, valence, and dominance.

Recommended citation: Wagner, J., Triantafyllopoulos, A., et al. (2023). "Dawn of the Transformer Era in Speech Emotion Recognition: Closing the Valence Gap" IEEE Transactions on Pattern Analysis and Machine Intelligence. vol. 45, no. 9, pp. 10745-10759.
Download Paper