Statistical Pronunciation Adaptation for Spontaneous Speech Synthesis - Inria - Institut national de recherche en sciences et technologies du numérique
Conference Papers Year : 2017

Statistical Pronunciation Adaptation for Spontaneous Speech Synthesis

Abstract

To bring more expressiveness into text-to-speech systems, this paper presents a new pronunciation variant generation method which works by adapting standard, i.e., dictionary-based, pronunciations to a spontaneous style. Its strength and originality lie in exploiting a wide range of linguistic, articulatory and prosodic features, and in using a probabilistic machine learning framework, namely conditional random fields and phoneme-based n-gram models. Extensive experiments on the Buckeye corpus of English conversational speech demonstrate the effectiveness of the approach through objective and perceptual evaluations.
Fichier principal
Vignette du fichier
pronunciation_adaptation_raheel.pdf (288.42 Ko) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

hal-01532035 , version 1 (02-06-2017)

Identifiers

  • HAL Id : hal-01532035 , version 1

Cite

Raheel Qader, Gwénolé Lecorvé, Damien Lolive, Marie Tahon, Pascale Sébillot. Statistical Pronunciation Adaptation for Spontaneous Speech Synthesis. Text, Speech and Dialogue (TSD), Aug 2017, Prague, Czech Republic. ⟨hal-01532035⟩
576 View
327 Download

Share

More