Bibliothèque - Voir fiche   Pour savoir plus sur cette section

Bertsokantari : a TTS based singing synthesis system

Document: Anglais. Online Fond de bibliothèque
Auteur(s)
Blanco Sierra, Eder del ; Erro, Daniel ; Hernaez, Inma ; Navas Cordón, Eva ; Sarasola, Xabier
Titre
Bertsokantari : a TTS based singing synthesis system / Eder del Blanco, Inma Hernaez, Eva Navas, Xabier Sarasola, Daniel Erro
Publication
San Francisco: , 2016
Thèmes
Bertsolaritza
Content
Testu osoa
Autres auteurs
EHU. Aholab taldea ; Ikerbasque
Typologie
Document
Eduki mota
Jardunaldiak, biltzarrak
ISBN / ISSN
1240 - 1244
Notes
Erreferentzia bibliografikoak: 1243-1244 or.
This paper describes the implementation of the Aholab entry for the Singing Synthesis Challenge: Fill-in the Gap. Our approach in this work makes use of an HTS based Text-to-Speech (TTS) synthesizer for Basque to generate the singing voice. The prosody related parameters provided by the TTS system for a spoken version of the score are modified to adapt them to the requirements of the music score concerning syllables duration and tone, while the spectral parameters are basically maintained. The paper describes the processing details developed to improve the quality of the output signal: the syllable timing, the generation of the intonation with vibrato and the manipulation of the model states. In this entry, the lyrics have been freely translated into Basque and the rhythm has been adapted to a Basque traditional rhythm.