Skip to content

Detail of publication

Citation

Tihelka, D. and Romportl, J. : Exploring Automatic Similarity Measures for Unit Selection Tuning . INTERSPEECH 2009, proceedings of 10th Annual Conference of International Speech Communication Association, p. 736-739, ISCA, Brighton, Great Britain, 2009.

Download PDF

PDF

Abstract

The present paper focuses on the current handling of target features in the unit selection approach basically requiring huge corpora. In the paper there are outlined possible solutions based on measuring (dis)similarity among prosodic patterns. As the start of research, the feasibility of (dis)similarity estimation is examined on several intuitively chosen measures of acoustic signal which are correlated to perceived similarity obtained from a large-scale listening test.

Detail of publication

Title: Exploring Automatic Similarity Measures for Unit Selection Tuning
Author: Tihelka, D. ; Romportl, J.
Language: English
Date of publication: 6 Sep 2009
Year: 2009
Type of publication: Papers in proceedings of reviewed conferences
Book title: INTERSPEECH 2009, proceedings of 10th Annual Conference of International Speech Communication Association
Page: 736 - 739
ISSN: 1990-9772
Publisher: ISCA
Address: Brighton, Great Britain
Date: 6 Sep 2009 - 10 Sep 2009
/ 2012-05-25 15:20:08 /

Keywords

speech synthesis, unit selection, target features, prosodic patterns, perceived similarity, signal similarity, multidimensional scaling

BibTeX

@INPROCEEDINGS{TihelkaD_2009_ExploringAutomatic,
 author = {Tihelka, D. and Romportl, J.},
 title = {Exploring Automatic Similarity Measures for Unit Selection Tuning},
 year = {2009},
 publisher = {ISCA},
 address = {Brighton, Great Britain},
 pages = {736-739},
 booktitle = {INTERSPEECH 2009, proceedings of 10th Annual Conference of International Speech Communication Association},
 ISSN = {1990-9772},
 url = {http://www.kky.zcu.cz/en/publications/TihelkaD_2009_ExploringAutomatic},
}