Ahots kantatuaren sintesiaren egokitzapena bertsolaritzarako
No Thumbnail Available
Date
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Ondorengo paper-ak euskarazko bertsolaritza ahots kantari sintetikoaren sortzeko prozesua deskribatzendu. Bertan, helburu hau lortzeko erabili diren baliabideen eta tresnen deskribapena emango da. Guresistemak Hidden Markov Model (HMM) bidezko hizketa-sistema estatistikoa oinarri bezala hartzendu ahots kantatua sortzeko.HMM-ak entrenatzeko hizketa datu-base bat erabili beharrean ahotskantatuaren datu-base batez entrenatuko da ezaugarri linguistikoez gain ezaugarri musikalak gehituzaudio seinaleei.
This paper describes the process of creation of a singing voice synthesis system for bertsolaritza, the artof singing improvised songs in Basque. The database acquisition process and the tools used to achievethis goal are explained. Our system uses Hidden Markov Model (HMM) based statistical speech synthesisas base to build a singing voice. We use a singing voice database instead of a speech database to trainthe HMM system with music labels in addition to the usual linguistic labels.
This paper describes the process of creation of a singing voice synthesis system for bertsolaritza, the artof singing improvised songs in Basque. The database acquisition process and the tools used to achievethis goal are explained. Our system uses Hidden Markov Model (HMM) based statistical speech synthesisas base to build a singing voice. We use a singing voice database instead of a speech database to trainthe HMM system with music labels in addition to the usual linguistic labels.
Description
Keywords
Euskarazko ahots-kantatu sintesia, HMM bidezko sintesia, Bertsolaritza, Basque singing synthesis, HMM-based singing synthesis, Bertsolaritza