musique contemporaine

Ircam - articles scientifiques notice originale

HMM-based Prosodic Structure Model Using Rich Linguistic Context

Type

text
 

Genre(s)

article
 

Forme(s)

document numérique
 

Cette ressource est disponible chez l'organisme suivant : Ircam - Centre Pompidou

Identification

Titre

HMM-based Prosodic Structure Model Using Rich Linguistic Context
 

Nom(s)

Obin, Nicolas (auteur)
 
Rodet, Xavier (auteur)
 
Lacheret, Anne (auteur)
 

Publication

Makuhari, Japan , 2010
 

Description

Sujet(s)

Prosody   Prosodic Structure   Speech Synthesis   High-Level Syntactical Analysis.
 

Résumé

This paper presents a study on the use of deep syntactical features to improve prosody modeling. A French linguistic processing chain based on linguistic preprocessing, morpho-syntactical labeling, and deep syntactical parsing is used in order to extract syntactical features from an input text. These features are used to define more or less high-level syntactical feature sets. Such feature sets are compared on the basis of a HMM-based prosodic structure model. High-level syntactical features are shown to significantly improve the performance of the model (up to 21% error reduction combined with 19% BIC reduction).
 

Note(s)

Contribution au colloque ou congrès : Interspeech
 

Localisation

Envoyer la notice

Bookmark and Share 
 

Identifiant OAI

 

Date de la notice

2010-07-02 02:00:00
 

Identifiant portail

 

Contact