Comparaison de trois outils de détection automatique de proéminences en français parlé
Résumé
This paper presents the inner details of three different
algorithms for prominence detection. On the basis of a 50-
minute corpus made of five speaking styles and manually
annotated for prominence, a quantitative evaluation
compares the three approaches.
algorithms for prominence detection. On the basis of a 50-
minute corpus made of five speaking styles and manually
annotated for prominence, a quantitative evaluation
compares the three approaches.
Domaines
LinguistiqueOrigine | Fichiers produits par l'(les) auteur(s) |
---|
Loading...