Improvements of Hungarian Hidden Markov Model-based text-to-speech synthesis

Improvements of Hungarian Hidden Markov Model-based text-to-speech synthesis

Statistical parametric, especially Hidden Markov Model-based, text-to-speech (TTS) synthesis has received much attention recently. The quality of HMM-based speech synthesis approaches that of the state-of-the-art unit selection systems and possesses numerous favorable features, e.g. small runtime fo...

Teljes leírás

Elmentve itt :
Bibliográfiai részletek
Szerzők: Tóth Bálint
Németh Géza
Testületi szerző: Conference on Hungarian Computational Linguistics (7.) (2010) (Szeged)
Dokumentumtípus: Cikk
Megjelent: 2010
Sorozat:Acta cybernetica 19 No. 4
Kulcsszavak:Számítástechnika, Nyelvészet - számítógép alkalmazása
Tárgyszavak:
Természettudományok
Számítás- és információtudomány
Bölcsészettudományok
Nyelvek és irodalom
Online Access:http://acta.bibl.u-szeged.hu/12890
Leíró adatok
Tartalmi kivonat:Statistical parametric, especially Hidden Markov Model-based, text-to-speech (TTS) synthesis has received much attention recently. The quality of HMM-based speech synthesis approaches that of the state-of-the-art unit selection systems and possesses numerous favorable features, e.g. small runtime footprint, speaker interpolation, speaker adaptation. This paper presents the improvements of a Hungarian HMM-based speech synthesis system, including speaker dependent and adaptive training, speech synthesis with pulse-noise and mixed excitation. Listening tests and their evaluation are also described.
Terjedelem/Fizikai jellemzők:715-731
ISSN:0324-721X

Hasonló tételek