A Multi-Task, Multi-Modal Approach for Predicting Categorical and Dimensional Emotions

no code implementations • 31 Dec 2023 • Alex-Răzvan Ispas, Théo Deschamps-Berger, Laurence Devillers

Speech emotion recognition (SER) has received a great deal of attention in recent years in the context of spontaneous conversations.

Multi-Task Learning Speech Emotion Recognition

Multiscale Contextual Learning for Speech Emotion Recognition in Emergency Call Center Conversations

no code implementations • 28 Aug 2023 • Théo Deschamps-Berger, Lori Lamel, Laurence Devillers

This paper presents a multi-scale conversational context learning approach for speech emotion recognition, which takes advantage of this hypothesis.

Speech Emotion Recognition

Exploring Attention Mechanisms for Multimodal Emotion Recognition in an Emergency Call Center Corpus

no code implementations • 12 Jun 2023 • Théo Deschamps-Berger, Lori Lamel, Laurence Devillers

Two pre-trained models based on speech and text were fine-tuned for speech emotion recognition.

Decision Making Multimodal Emotion Recognition +1

End-to-End Speech Emotion Recognition: Challenges of Real-Life Emergency Call Centers Data Recordings

no code implementations • 28 Oct 2021 • Théo Deschamps-Berger, Lori Lamel, Laurence Devillers

Using the same end-to-end deep learning architecture, an Unweighted Accuracy Recall (UA) of 63% is obtained on IEMOCAP and a UA of 45. 6% on CEMO, each with 4 classes.

Speech Emotion Recognition