Přejít na obsah

Publikace

Detail publikace

Citace

Přibil, J and Přibilová, A and Matoušek, J. : Experiment with GMM-Based Artefact Localization in Czech Synthetic Speech . Text, Speech, and Dialogue, 18th International Conference, TSD 2015, Lecture Notes in Artificial Intelligence, vol. 9302, p. 23-31, Springer, 2015.

Další informace


Springerlink

Abstrakt

The paper describes an experiment with using the statistical approach based on the Gaussian mixture models (GMM) for localization of artefacts in the synthetic speech produced by the Czech text-to-speech system employing the unit selection principle. In addition, the paper analyzes influence of different number of used GMM mixtures, and the influence of setting of the frame shift during the spectral feature analysis on the resulting artefact position accuracy. Obtained results of performed experiments confirm proper function of the chosen concept and the presented artefact position localizer can be used as an alternative to the standardly applied manual localization method.

Detail publikace

Název: Experiment with GMM-Based Artefact Localization in Czech Synthetic Speech
Autor: Přibil, J ; Přibilová, A ; Matoušek, J.
Název - česky: Experiment s lokalizací artefaktů v české syntetické řeči pomocí GMM
Jazyk publikace: anglicky
Datum vydání: 14.9.2015
Rok vydání: 2015
Typ publikace: Kapitola v knize
Název knihy: Text, Speech, and Dialogue, 18th International Conference, TSD 2015
Svazek: Lecture Notes in Artificial Intelligence
Číslo vydání: 9302
Strana: 23 - 31
DOI: 10.1007/978-3-319-24033-6_3
ISBN: 978-3-319-24032-9
ISSN: 0302-9743
Nakladatel: Springer
Datum: 14.9.2015 - 17.9.2015
/ 2016-01-13 17:22:38 /

Klíčová slova

quality of synthetic speech, text-to-speech system, GMM classification, statistical analysis

BibTeX

@INCOLLECTION{PribilJ_2015_Experimentwith,
 author = {P\v{r}ibil, J and P\v{r}ibilov\'{a}, A and Matou\v{s}ek, J.},
 title = {Experiment with GMM-Based Artefact Localization in Czech Synthetic Speech },
 year = {2015},
 publisher = {Springer},
 volume = {9302},
 pages = {23-31},
 booktitle = {Text, Speech, and Dialogue, 18th International Conference, TSD 2015},
 series = {Lecture Notes in Artificial Intelligence},
 ISBN = {978-3-319-24032-9},
 ISSN = {0302-9743},
 doi = {10.1007/978-3-319-24033-6_3},
 url = {http://www.kky.zcu.cz/en/publications/PribilJ_2015_Experimentwith},
}