Reconstruction-error-based learning for continuous emotion recognition in speech - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2017

Reconstruction-error-based learning for continuous emotion recognition in speech

Résumé

To advance the performance of continuous emotion recognition from speech, we introduce a reconstruction-error-based (RE-based) learning framework with memory-enhanced Recurrent Neural Networks (RNN). In the framework, two successive RNN models are adopted, where the first model is used as an autoencoder for reconstructing the original features, and the second is employed to perform emotion prediction. The RE of the original features is used as a complementary descriptor, which is merged with the original features and fed to the second model. The assumption of this framework is that the system has the ability to learn its 'drawback' which is expressed by the RE. Experimental results on the RECOLA database show that the proposed framework significantly outperforms the baseline systems without any RE information in terms of Concordance Correlation Coefficient (.729 vs .710 for arousal, .360 vs .237 for valence), and also significantly overcomes other state-of-the-art methods.
Fichier principal
Vignette du fichier
Han17-RLF.pdf (368.31 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01494058 , version 1 (22-03-2017)

Licence

Domaine public

Identifiants

  • HAL Id : hal-01494058 , version 1

Citer

Jing Han, Zixing Zhang, Fabien Ringeval, Björn Schuller. Reconstruction-error-based learning for continuous emotion recognition in speech. Proceedings of the 42nd IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2017, La Nouvelle Orléans (LA), United States. ⟨hal-01494058⟩
333 Consultations
511 Téléchargements

Partager

Gmail Facebook X LinkedIn More