Skip to Main content Skip to Navigation
Theses

Évaluation expérimentale d'un système statistique de synthèse de la parole, HTS, pour la langue française

Sébastien Le Maguer 1
1 CORDIAL - Human-machine spoken dialogue
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, INRIA Rennes, ENSSAT - École Nationale Supérieure des Sciences Appliquées et de Technologie
Abstract : The work presented in this thesis is about TTS speech synthesis and, more particularly, about statistical speech synthesis for French. We present an analysis on the impact of the linguistic contextual factors on the synthesis achieved by the HTS statistical speech synthesis system. To conduct the experiments, two objective evaluation protocols are proposed. The first one uses Gaussian mixture models (GMM) to represent the acoustical space produced by HTS according to a contextual feature set. By using a constant reference set of natural speech stimuli, GMM can be compared between themselves and consequently acoustic spaces generated by HTS. The second objective evaluation that we propose is based on pairwise distances between natural speech and synthetic speech generated by HTS. Results obtained by both protocols, and confirmed by subjective evaluations, show that using a large set of contextual factors does not necessarily improve the modeling and could be counter-productive on the speech quality.
Document type :
Theses
Complete list of metadatas

Cited literature [38 references]  Display  Hide  Download

https://tel.archives-ouvertes.fr/tel-00913565
Contributor : Abes Star :  Contact
Submitted on : Tuesday, January 21, 2014 - 3:12:08 PM
Last modification on : Thursday, January 7, 2021 - 4:13:39 PM
Long-term archiving on: : Tuesday, April 22, 2014 - 9:55:54 AM

File

LE_MAGUER_Sebastien.pdf
Version validated by the jury (STAR)

Identifiers

  • HAL Id : tel-00913565, version 2

Citation

Sébastien Le Maguer. Évaluation expérimentale d'un système statistique de synthèse de la parole, HTS, pour la langue française. Autre [cs.OH]. Université Rennes 1, 2013. Français. ⟨NNT : 2013REN1S088⟩. ⟨tel-00913565v2⟩

Share

Metrics

Record views

495

Files downloads

444