IRIT-MFU Multi-modal systems for emotion classification for Odyssey 2024 challenge - Structuration, Analyse et Modélisation de documents Vidéo et Audio Access content directly
Conference Papers Year : 2024

IRIT-MFU Multi-modal systems for emotion classification for Odyssey 2024 challenge

Jérôme Bertrand
  • Function : Author
  • PersonId : 1387276
Marie-Françoise Bertrand
  • Function : Author

Abstract

In this paper, we present our contribution to emotion classifi- cation in speech as part of our participation in Odyssey 2024 challenge. We propose a hybrid system that takes advantage of both audio signal information and semantic information ob- tained from automatic transcripts. We propose several models for each modality and three different fusion methods for the classification task. The results show that multimodality im- proves significantly the performance and allows us surpassing the challenge baseline, which is an audio only system, from a 0.311 macro F1-score to 0.337.
Fichier principal
Vignette du fichier
Odyssey2024_vFinale.pdf (608.81 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04594287 , version 1 (30-05-2024)

Licence

Identifiers

Cite

Adrien Lafore, Clément Pagés, Leila Moudjari, Sebastião Quintas, Hervé Bredin, et al.. IRIT-MFU Multi-modal systems for emotion classification for Odyssey 2024 challenge. Odyssey 2024: The Speaker and Language Recognition Workshop, Jun 2024, Québec, Canada. pp.296-302, ⟨10.21437/odyssey.2024-42⟩. ⟨hal-04594287⟩
157 View
15 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More