Towards Glottal Source Controllability in Expressive Speech Synthesis - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2012

Towards Glottal Source Controllability in Expressive Speech Synthesis

Résumé

In order to obtain more human like sounding human- machine interfaces we must first be able to give them expressive capabilities in the way of emotional and stylistic features so as to closely adequate them to the intended task. If we want to replicate those features it is not enough to merely replicate the prosodic information of fundamental frequency and speaking rhythm. The proposed additional layer is the modification of the glottal model, for which we make use of the GlottHMM parameters. This paper analyzes the viability of such an approach by verifying that the expressive nuances are captured by the aforementioned features, obtaining 95% recognition rates on styled speaking and 82% on emotional speech. Then we evaluate the effect of speaker bias and recording environment on the source modeling in order to quantify possible problems when analyzing multi-speaker databases. Finally we propose a speaking styles separation for Spanish based on prosodic features and check its perceptual significance.
Fichier principal
Vignette du fichier
index.pdf (249.47 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01161011 , version 1 (08-06-2015)

Identifiants

  • HAL Id : hal-01161011 , version 1

Citer

Jaime Lorenzo-Trueba, Roberto Barra-Chicote, Tuomo Raitio, Nicolas Obin, Paavo Alku, et al.. Towards Glottal Source Controllability in Expressive Speech Synthesis. Interspeech, 2012, Portland, United States. pp.1-1. ⟨hal-01161011⟩
147 Consultations
86 Téléchargements

Partager

Gmail Facebook X LinkedIn More