Exploiting Alternatives for Text-To-Speech Synthesis: From Machine to Human - Archive ouverte HAL Accéder directement au contenu
Chapitre D'ouvrage Année : 2015

Exploiting Alternatives for Text-To-Speech Synthesis: From Machine to Human

Résumé

he absence of alternatives/variants is a dramatical limitation of text-to- speech synthesis compared to the variety of human speech. This paper introduces the use of speech alternatives/variants in order to improve text-to-speech synthesis systems. Speech alternatives denote the variety of possibilities that a speaker has to pronounce a sentence - depending on linguistic constraints, specific strategies of the speaker, speaking style, and pragmatic constraints. During the training, symbolic and acoustic characteristics of a unit-selection speech synthesis system are statisti- cally modelled with context-dependent parametric models (GMMs/HMMs). During the synthesis, symbolic and acoustic alternatives are exploited using a GENERALIZED VITERBI ALGORITHM (GVA) to determine the sequence of speech units used for the synthesis. Objective and subjective evaluations support evidence that the use of speech alternatives significantly improves speech synthesis over conventional speech synthesis systems. Beyond, speech alternatives can also be used to vary the speech synthesis for a given text. The proposed method can easily be extended to HMM-based speech synthesis.
Fichier principal
Vignette du fichier
springer2015_NO_CV.pdf (1.9 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01164642 , version 1 (22-06-2015)

Identifiants

Citer

Nicolas Obin, Christophe Veaux, Pierre Lanchantin. Exploiting Alternatives for Text-To-Speech Synthesis: From Machine to Human. Springer Berlin Heidelberg. Speech Prosody in Speech Synthesis: Modeling and Generation of Prosody for High Quality and Flexible Speech Synthesis, pp.189-202, 2015, Prosody, Phonology and Phonetics, 978-3-662-45258-5. ⟨10.1007/978-3-662-45258-5_13⟩. ⟨hal-01164642⟩
246 Consultations
238 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More