Přejít na obsah

Detail publikace

Citace

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.

PDF ke stažení

PDF

Abstrakt

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 publikace

Název: Exploring Automatic Similarity Measures for Unit Selection Tuning
Autor: Tihelka, D. ; Romportl, J.
Jazyk publikace: anglicky
Datum vydání: 6.9.2009
Rok vydání: 2009
Typ publikace: Stať ve sborníku
Název knihy: INTERSPEECH 2009, proceedings of 10th Annual Conference of International Speech Communication Association
Strana: 736 - 739
ISSN: 1990-9772
Nakladatel: ISCA
Místo vydání: Brighton, Great Britain
Datum: 6.9.2009 - 10.9.2009
/ 2012-05-25 15:20:08 /

Klíčová slova

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},
}