Skip to content

Detail of publication

Citation

Matoušek, J. : On Minimizing the Size of Speech Unit Database in Concatenative Speech Synthesis . Speech Processing, proceedings of the 16th Czech-German Workshop, p. 70-76, Institute of Radio Engineering and Electronics AS CR, Prague, 2006.

Abstract

In this paper, minimization of speech unit database is researched in order to have a compact speech unit database yielding a "good enough" synthetic speech usable also for low-resource devices. We focused mainly on HMM-based speech unit database preparation, a process which prepares a set of context-dependent phones (triphones) by means of HMM modelling, CART-based clustering, and HMM-based segmentation in a fully automatic way. Three experiments are described in the paper: the first one concerns the size of the source speech corpus, the second one deals with the triphone clustering process, and the last one concerns the modelling of the cross-word dependencies. The final minimised system exploits techniques used in all three experiments. The size of the resulting speech unit database decreased from 28.1 to 1.6 MB. The resulting synthetic speech was then judged by means of CCR listening tests and evaluated as "slightly worse" than speech generated by the baseline system.

Detail of publication

Title: On Minimizing the Size of Speech Unit Database in Concatenative Speech Synthesis
Author: Matoušek, J.
Language: English
Date of publication: 27 Sep 2006
Year: 2006
Type of publication: Papers in proceedings of reviewed conferences
Book title: Speech Processing, proceedings of the 16th Czech-German Workshop
Page: 70 - 76
ISBN: 80-86269-15-9
Publisher: Institute of Radio Engineering and Electronics AS CR
Address: Prague
Date: 27 Sep 2006 - 29 Sep 2006
/ 2008-05-20 10:01:19 /

Keywords

speech synthesis, minimization of speech unit database, HMM modelling, HMM-based segmentation, CART clustering

BibTeX

@INPROCEEDINGS{MatousekJ_2006_OnMinimizingthe,
 author = {Matou\v{s}ek, J.},
 title = {On Minimizing the Size of Speech Unit Database in Concatenative Speech Synthesis},
 year = {2006},
 publisher = {Institute of Radio Engineering and Electronics AS CR},
 address = {Prague},
 pages = {70-76},
 booktitle = {Speech Processing, proceedings of the 16th Czech-German Workshop},
 ISBN = {80-86269-15-9},
 url = {http://www.kky.zcu.cz/en/publications/MatousekJ_2006_OnMinimizingthe},
}