Transformer-Based Self-Supervised Learning for Emotion Recognition - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Transformer-Based Self-Supervised Learning for Emotion Recognition

Grégoire Lefebvre
Julien Cumin
  • Fonction : Auteur
  • PersonId : 977626

Résumé

In order to exploit representations of time-series signals, such as physiological signals, it is essential that these representations capture relevant information from the whole signal. In this work, we propose to use a Transformer-based model to process electrocardiograms (ECG) for emotion recognition. Attention mechanisms of the Transformer can be used to build contextualized representations for a signal, giving more importance to relevant parts. These representations may then be processed with a fully-connected network to predict emotions. To overcome the relatively small size of datasets with emotional labels, we employ self-supervised learning. We gathered several ECG datasets with no labels of emotion to pre-train our model, which we then fine-tuned for emotion recognition on the AMIGOS dataset. We show that our approach reaches state-of-the-art performances for emotion recognition using ECG signals on AMIGOS. More generally, our experiments show that transformers and pre-training are promising strategies for emotion recognition with physiological signals.
Fichier principal
Vignette du fichier
Trnsf_based_EmoRec.pdf (193.75 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03634490 , version 1 (07-04-2022)
hal-03634490 , version 2 (01-06-2022)

Identifiants

Citer

Juan Vazquez-Rodriguez, Grégoire Lefebvre, Julien Cumin, James L. Crowley. Transformer-Based Self-Supervised Learning for Emotion Recognition. 26th International Conference on Pattern Recognition (ICPR 2022), Aug 2022, Montreal, Canada. ⟨hal-03634490v2⟩
204 Consultations
321 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More