Emotion recognition from raw speech signals using 2D CNN with deep metric learning - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Emotion recognition from raw speech signals using 2D CNN with deep metric learning

Résumé

In this paper we have introduced a novel emotion recognition framework from raw speech signals. The system is based on ResNet architecture fed with spectrogram inputs. The CNN is further extended with a GhostVLAD feature aggregation layer that extracts a single, fixed size descriptor constructed at the level of the utterance. The system adopts a sentiment metric loss that integrates the relations between various classes of emotions. The experimental evaluation conducted on two publicly available databases: RAVDESS and CREMA-D validates the proposed methodology with average accuracy scores of 82% and 63%, respectively.
Fichier non déposé

Dates et versions

hal-03937087 , version 1 (13-01-2023)

Identifiants

Citer

Bogdan Mocanu, Ruxandra Tapu. Emotion recognition from raw speech signals using 2D CNN with deep metric learning. 2022 IEEE International Conference on Consumer Electronics (ICCE), Jan 2022, Las Vegas, United States. pp.1-5, ⟨10.1109/ICCE53296.2022.9730534⟩. ⟨hal-03937087⟩
12 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More