| HAL : halshs-00419977, version 1 |
| Fiche détaillée | Récupérer au format |
|
|
| Speech and Computer, Russie, Fédération De (2009) |
|
|
|
|
| A Syllable-Based Prominence Detection Model Based on Discriminant Analysis and Context-Dependency |
|
|
| Nicolas Obin 1Xavier Rodet 1 |
|
|
| (21/06/2009) |
|
|
| On the basis of our previous work, we propose a syllablebased prominence detection model within the framework of exploratory data analysis and discriminant learning in the acoustic domain. This paper investigates two hypothesis on the acoustic data processing: a linear discriminant analysis in which the relative discriminant ability of single prosodic cues are combined into prosodic patterns and a context-dependant model that accounts for phonological dependencies (phonetic intrinsic properties and coarticulation effect). The proposed approach significantly outperforms a baseline method on a corpus of French read speech with a performance of 87.5% in f-measure for the prominent syllables (respectively 90.4% in global accuracy). |
|
|
|
|
|
|
|
|
|
|
| 1 : | Sciences et Technologies de la Musique et du Son (STMS) |
| IRCAM – CNRS : UMR9912 – Université Pierre et Marie Curie [UPMC] - Paris VI | |
| 2 : | Modèles, Dynamiques, Corpus (MoDyCo) |
| CNRS : UMR7114 – Université Paris X - Paris Ouest Nanterre La Défense | |
|
|
|
|
|
|
|
|
| Discipline | : | Sciences de l'Homme et Société/Linguistique Statistiques/Machine Learning Sciences de l'ingénieur/Traitement du signal et de l'image Informatique/Traitement du signal et de l'image |
|
|
| syllable prominence – automatic detection – prosody |
|
|
| Liste des fichiers attachés à ce document : | |||||
|
|
|
| halshs-00419977, version 1 | |
| http://halshs.archives-ouvertes.fr/halshs-00419977 | |
| oai:halshs.archives-ouvertes.fr:halshs-00419977 | |
| Contributeur : Nicolas Obin | |
| Soumis le : Vendredi 25 Septembre 2009, 21:43:50 | |
| Dernière modification le : Mardi 29 Septembre 2009, 09:01:49 | |