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

Tóth, Bálint and Németh, Géza: Improvements of Hungarian Hidden Markov Model-based text-to-speech synthesis. Acta cybernetica, (19) 4. pp. 715-731. (2010)

[img] Cikk, tanulmány, mű
TothB_2010_ActaCybernetica.pdf

Download (561kB)

Abstract

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.

Item Type: Article
Event Title: Conference on Hungarian Computational Linguistics, 7., 2010, Szeged
Journal or Publication Title: Acta cybernetica
Date: 2010
Volume: 19
Number: 4
Page Range: pp. 715-731
ISSN: 0324-721X
Language: angol
Uncontrolled Keywords: Természettudomány, Informatika, Nyelvtudomány
Additional Information: Bibliogr.: p. 729-731.; Abstract
Date Deposited: 2016. Oct. 15. 12:24
Last Modified: 2018. Jun. 06. 12:38
URI: http://acta.bibl.u-szeged.hu/id/eprint/12890

Actions (login required)

View Item View Item