The IRISA Text-To-Speech System for the Blizzard Challenge 2015 - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2015

The IRISA Text-To-Speech System for the Blizzard Challenge 2015

Résumé

This paper describes the implementation of the IRISA unit selection-based TTS system for our participation in the Blizzard Challenge 2015. For our first participation, we chose to take part in the first task by building one voice for each of the 5 Indian languages out of the 6 requested (Bengali, Hindi, Malayalam, Tamil and Telugu). We describe the process followed to build the voices from given data and the architecture of our system. In particular, we introduce a penalty in the concatenation cost, inherited from the field of corpus covering, in order to block some concatenations based on their phonological class. Moreover, a fuzzy function is proposed to relax the penalty based on the concatenation quality with respect to the cost distribution. Considering that no language specific processing has been done and that we had never worked with Indian languages, results are very satisfying.
Fichier non déposé

Dates et versions

hal-01196168 , version 1 (09-09-2015)

Identifiants

  • HAL Id : hal-01196168 , version 1

Citer

Pierre Alain, Jonathan Chevelu, David Guennec, Gwénolé Lecorvé, Damien Lolive. The IRISA Text-To-Speech System for the Blizzard Challenge 2015. Blizzard Challenge 2015 Workshop, Sep 2015, Berlin, Germany. 4 p., 2 columns. ⟨hal-01196168⟩
223 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More