Přejít na obsah

Detail publikace

Citace

Přibil, J and Přibilová, A and Matoušek, J. : GMM Classification of Text-to-Speech Synthesis: Identification of Original Speaker’s Voice . Text, Speech, and Dialogue, 17th International Conference, TSD 2014, Brno, Czech Republic, September 8-12, 2014. Proceedings, Lecture Notes in Artificial Intelligence, vol. 8655, p. 365-373, Springer, 2014.

Další informace


Springerlink

Abstrakt

This paper describes two experiments. The first one deals with evaluation of synthetic speech quality by reverse identification of original speakers whose voices had been used for several Czech text-to-speech (TTS) systems. The second experiment was aimed at evaluation of the influence of voice transformation on the original speaker recognition. The paper further describes an analysis of the influence of initial settings for creation and training of the Gaussian mixture models (GMM), and the influence of different types of used speech features (spectral and/or supra-segmental) on correctness of GMM identification. The stability of the identification process with respect to the duration of the tested sentence (number of the processed frames) was analysed, too.

Detail publikace

Název: GMM Classification of Text-to-Speech Synthesis: Identification of Original Speaker’s Voice
Autor: Přibil, J ; Přibilová, A ; Matoušek, J.
Název - česky: Klasifikace syntézy řeči z textu pomocí GMM: Identifikace původního hlasu řečníka
Jazyk publikace: česky
Datum vydání: 8.9.2014
Rok vydání: 2014
Typ publikace: Stať ve sborníku
Název knihy: Text, Speech, and Dialogue, 17th International Conference, TSD 2014, Brno, Czech Republic, September 8-12, 2014. Proceedings
Svazek: Lecture Notes in Artificial Intelligence
Číslo vydání: 8655
Strana: 365 - 373
DOI: 10.1007/978-3-319-10816-2_44
ISBN: 978-3-319-10815-5
ISSN: 0302-9743
Nakladatel: Springer
Datum: 8.9.2014 - 12.9.2014
/ 2016-01-13 17:10:33 /

Klíčová slova

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

BibTeX

@INCOLLECTION{PribilJ_2014_GMMClassificationof,
 author = {P\v{r}ibil, J and P\v{r}ibilov\'{a}, A and Matou\v{s}ek, J.},
 title = {GMM Classification of Text-to-Speech Synthesis: Identification of Original Speaker's Voice},
 year = {2014},
 publisher = {Springer},
 volume = {8655},
 pages = {365-373},
 booktitle = {Text, Speech, and Dialogue, 17th International Conference, TSD 2014, Brno, Czech Republic, September 8-12, 2014. Proceedings},
 series = {Lecture Notes in Artificial Intelligence},
 ISBN = {978-3-319-10815-5},
 ISSN = {0302-9743},
 doi = {10.1007/978-3-319-10816-2_44},
 url = {http://www.kky.zcu.cz/en/publications/PribilJ_2014_GMMClassificationof},
}