Beat gesture prediction using prosodic features

Abstract :

In this work we present a machine learning approach to gesture prediction using prosodic features. We use conditional random fields to predict the presence of beat gestures using the following prosodic features: pitch, pitch-derivatives, intensity and absence or presence of syllable nuclei. These features are calculated over overlapping sliding windows big enough to average out the high frequency variations associated with pitch and intensity at the syllable level. We found that the results improve remarkably when the classification is treated as a multi-class problem as opposed to a binary problem with the two classes: presence and absence of gesture.

Type de document :
Communication dans un congrès
3rd International Workshop on Virtual Social Interaction (VSI 2017), Jul 2017, Bielefeld, Germany. 3rd International Workshop on Virtual Social Interaction (VSI 2017), 2017
Liste complète des métadonnées

https://hal-imt.archives-ouvertes.fr/hal-01567617
Contributeur : Admin Télécom Paristech <>
Soumis le : lundi 24 juillet 2017 - 10:52:58
Dernière modification le : mercredi 21 mars 2018 - 18:57:40

Identifiants

  • HAL Id : hal-01567617, version 1

Citation

Varun Jain, Chloé Clavel, Catherine Pelachaud. Beat gesture prediction using prosodic features. 3rd International Workshop on Virtual Social Interaction (VSI 2017), Jul 2017, Bielefeld, Germany. 3rd International Workshop on Virtual Social Interaction (VSI 2017), 2017. 〈hal-01567617〉

Partager

Métriques

Consultations de la notice

96