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

Pierre Alain 1 Gwénolé Lecorvé 1 Damien Lolive 1 Antoine Perquin 1
1 EXPRESSION - Expressiveness in Human Centered Data/Media
UBS - Université de Bretagne Sud, IRISA-D6 - MEDIA ET INTERACTIONS
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.
Complete list of metadatas

Cited literature [23 references]  Display  Hide  Download

https://hal.inria.fr/hal-01998037
Contributor : Damien Lolive <>
Submitted on : Tuesday, January 29, 2019 - 1:30:16 PM
Last modification on : Thursday, February 7, 2019 - 5:04:34 PM
Long-term archiving on : Tuesday, April 30, 2019 - 3:34:32 PM

File

IRISA_BlizzardChallenge2018.pd...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01998037, version 1

Citation

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⟩

Share

Metrics

Record views

45

Files downloads

85