French Prominence, a probabilistic framework

Anne Lacheret (1) , Nicolas Obin (2) , Xavier Rodet (2)

1 MoDyCo - Modèles, Dynamiques, Corpus
2 STMS - Sciences et Technologies de la Musique et du Son

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.

Mots clés: French Prominence; probabilistic framework

Domaines: Linguistique

Anne Lacheret, Nicolas Obin, Xavier Rodet. French Prominence, a probabilistic framework. ICASSP'08, 2008, Las Vegas, Nevada, United States. non précisé. ⟨halshs-00360316⟩