The IRISA Text-To-Speech System for the Blizzard Challenge 2017 - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2017

The IRISA Text-To-Speech System for the Blizzard Challenge 2017


This paper describes the implementation of the IRISA unit selection-based TTS system for our participation to the Blizzard Challenge 2017. 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 DNN-based prosodic prediction and also a specific score to deal with narrative/direct speech parts. Unit selection is based on a Viterbi-based algorithm with preselection filters used to reduce the search space. A penalty is introduced in the concatenation cost to block some concatenations based on their phonological class. Moreover, a fuzzy function is used to relax this penalty based on the concatenation quality with respect to the cost distribution. Integrating a lot of constraints, this system achieves average results compared to others.
Fichier principal
Vignette du fichier
IRISA_Blizzard2017.pdf (177.4 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01662361 , version 1 (13-12-2017)


  • HAL Id : hal-01662361 , version 1


Damien Lolive, Pierre Alain, Nelly Barbot, Jonathan Chevelu, Gwénolé Lecorvé, et al.. The IRISA Text-To-Speech System for the Blizzard Challenge 2017. Blizzard Challenge, Aug 2017, Stockholm, Sweden. ⟨hal-01662361⟩
482 View
124 Download


Gmail Facebook X LinkedIn More