Generating German intonation with a trainable prosodic model - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2006

Generating German intonation with a trainable prosodic model

Résumé

A trainable prosodic model called SFC (Superposition of Functional Contours), proposed by Holm and Bailly, is here confronted to German intonation. Training material is the publicly available Siemens Synthesis Corpus that provides spoken utterances for high-quality speech synthesis. We describe the labeling framework and first evaluation results that compares the original prosody of test sentences of this corpus with their prosodic rendering by the proposed model and state-of-the-art systems available on-line on the web
Fichier principal
Vignette du fichier
gb_IS06.pdf (97.75 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00366490 , version 1 (08-03-2009)

Identifiants

  • HAL Id : hal-00366490 , version 1

Citer

Gérard Bailly, Ian Gorisch. Generating German intonation with a trainable prosodic model. Interspeech, Sep 2006, Pittsburgh, United States. pp.2366-2369. ⟨hal-00366490⟩

Collections

UGA CNRS ICP
78 Consultations
94 Téléchargements

Partager

Gmail Facebook X LinkedIn More