Fiche du document
26 février 2015
- handle: 10670/1.vgm7je
- isbn: 978-3-662-45258-5
- hal: hal-01164642
- doi: 10.1007/978-3-662-45258-5_13
Ce document est lié à :
info:eu-repo/semantics/altIdentifier/doi/10.1007/978-3-662-45258-5_13
info:eu-repo/semantics/OpenAccess
Mots-clés
Prosody Text-to-SpeechSujets proches
Speech--Synthesis Synthetic speech TalkingCiter ce document
Nicolas Obin et al., « Exploiting Alternatives for Text-To-Speech Synthesis: From Machine to Human », HAL-SHS : linguistique, ID : 10.1007/978-3-662-45258-5_13
Métriques
Partage / Export
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.