Audio Features Dedicated to the Detection of Four Basic Emotions

Abstract : In this paper, we decided to study the effect of extracted audio features, using the analysis tool Essentia, on the quality of constructed music emotion detection classifiers. The research process included constructing training data, feature extraction, feature selection, and building classifiers. We selected features and found sets of features that were the most useful for detecting individual emotions. We examined the effect of low-level, rhythm and tonal features on the accuracy of the constructed classifiers. We built classifiers for different combinations of feature sets, which enabled distinguishing the most useful feature sets for individual emotions.
Type de document :
Communication dans un congrès
Khalid Saeed; Władysław Homenda. 14th Computer Information Systems and Industrial Management (CISIM), Sep 2015, Warsaw, Poland. Springer, Lecture Notes in Computer Science, LNCS-9339, pp.583-591, 2015, Computer Information Systems and Industrial Management. 〈10.1007/978-3-319-24369-6_49〉
Liste complète des métadonnées

https://hal.inria.fr/hal-01444499
Contributeur : Hal Ifip <>
Soumis le : mardi 24 janvier 2017 - 10:41:42
Dernière modification le : mercredi 25 janvier 2017 - 01:04:03
Document(s) archivé(s) le : mardi 25 avril 2017 - 18:22:13

Fichier

978-3-319-24369-6_49_Chapter.p...
Fichiers produits par l'(les) auteur(s)

Licence


Distributed under a Creative Commons Paternité 4.0 International License

Identifiants

Citation

Jacek Grekow. Audio Features Dedicated to the Detection of Four Basic Emotions. Khalid Saeed; Władysław Homenda. 14th Computer Information Systems and Industrial Management (CISIM), Sep 2015, Warsaw, Poland. Springer, Lecture Notes in Computer Science, LNCS-9339, pp.583-591, 2015, Computer Information Systems and Industrial Management. 〈10.1007/978-3-319-24369-6_49〉. 〈hal-01444499〉

Partager

Métriques

Consultations de la notice

36

Téléchargements de fichiers

145