French Prominence, a probabilistic framework
Résumé
Identification of prosodic phenomena is of first importance
in prosodic analysis and modeling. We introduce in this paper
a new method for automatic prominence labelling. The
proposed method is based on well known machine learning
technics in a three step procedure : feature extraction, feature
selection for finding the more relevant prominence acoustic
correlates and gaussian mixture model for predicting prominence.
in prosodic analysis and modeling. We introduce in this paper
a new method for automatic prominence labelling. The
proposed method is based on well known machine learning
technics in a three step procedure : feature extraction, feature
selection for finding the more relevant prominence acoustic
correlates and gaussian mixture model for predicting prominence.
Domaines
LinguistiqueOrigine | Fichiers produits par l'(les) auteur(s) |
---|
Loading...