The IRISA Text-To-Speech System for the Blizzard Challenge 2018 - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2018

The IRISA Text-To-Speech System for the Blizzard Challenge 2018

Abstract

This paper describes the implementation of the IRISA unit selection-based TTS system for our participation to the Blizzard Challenge 2018. We describe the process followed to build the voice from given data and the architecture of our system. It uses a selection cost which integrates notably a bottleneck DNN-based embedding prediction. Unit selection is based on a Viterbi-based algorithm with preselection filters used to reduce the search space. The system achieves average results compared to others.
Fichier principal
Vignette du fichier
IRISA_BlizzardChallenge2018.pdf (267.84 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01998037 , version 1 (29-01-2019)

Identifiers

  • HAL Id : hal-01998037 , version 1

Cite

Pierre Alain, Gwénolé Lecorvé, Damien Lolive, Antoine Perquin. The IRISA Text-To-Speech System for the Blizzard Challenge 2018. Blizzard Challenge Workshop, Sep 2018, Hyderabad, India. ⟨hal-01998037⟩
97 View
116 Download

Share

Gmail Facebook X LinkedIn More