Extraction of emotional prosody from telephone calls to hospital emergency departments - Archive ouverte HAL Accéder directement au contenu
Proceedings/Recueil Des Communications Année : 2023

Extraction of emotional prosody from telephone calls to hospital emergency departments

Résumé

This study is based on the exploitation of telephone calls to hospital emergency departments in order to train artificial intelligence tools for the automatic recognition of vocal emotions for the purpose of improving emergency medical regulation. The main objective is to extract the most characteristic acoustic cues of vocal emotions. Very limited samples were selected from the audio databases of two University Hospitals in the Jura Arc (CHRU of Besançon in France and CHUV of Lausanne in Switzerland). Only extracts containing linguistic vocal emotions with a negative polarity (angst, anger, embarrassment and sadness) were retained for the study. These extracts were segmented and labeled, and their acoustic parameters (F0, intensity and duration) were measured manually. The preliminary results show that F0 modulations seem more accurate to discriminate the four vocal emotions.
Fichier non déposé

Dates et versions

hal-04182004 , version 1 (16-08-2023)

Identifiants

  • HAL Id : hal-04182004 , version 1

Citer

Dongjun Wei, Mohamed Embarki, Oussama Barakat, Coralie Vaucherey, Thibaut Desmettre, et al.. Extraction of emotional prosody from telephone calls to hospital emergency departments. 1, Guarant International., pp.1551-1555, 2023, Proceedings of the 20th International Congress of Phonetic Sciences, 978-80-908 114-2-3. ⟨hal-04182004⟩
47 Consultations
0 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More