Přejít na obsah

Detail publikace


Zdeněk Hanzlíček : Czech HMM-Based Speech Synthesis . Text, Speech and Dialogue, Lecture Notes in Computer Science, vol. 6231, p. 291-298, Springer Berlin / Heidelberg, 2010.


In this paper, first experiments on statistical parametric HMM-based speech synthesis for the Czech language are described. In this synthesis method, trajectories of speech parameters are generated from the trained hidden Markov models. A final speech waveform is synthesized from those speech parameters. In our experiments, spectral properties were represented by mel cepstrum coefficients. For the waveform synthesis, the corresponding MLSA filter excited by pulses or noise was utilized. Beside that basic setup, a high-quality analysis/synthesis system STRAIGHT was employed for more sophisticated speech representation. For a more robust model parameter estimation, HMMs are clustered by using decision tree-based context clustering algorithm. For this purpose, phonetic and prosodic contextual factors proposed for the Czech language are taken into account. The created clustering trees are also employed for synthesis of speech units unseen within the training stage. The evaluation by subjective listening tests showed that speech produced by the combination of HMM-based TTS system and STRAIGHT is of comparable quality as speech synthesised by the unit selection TTS system trained from the same speech data.

Detail publikace

Název: Czech HMM-Based Speech Synthesis
Autor: Zdeněk Hanzlíček
Jazyk publikace: anglicky
Datum vydání: 3.9.2010
Rok vydání: 2010
Typ publikace: Článek z časopisu
Název knihy: Text, Speech and Dialogue
Svazek: Lecture Notes in Computer Science
Číslo vydání: 6231
Strana: 291 - 298
ISBN: 978-3-642-15759-2
Nakladatel: Springer Berlin / Heidelberg
/ 2011-03-15 17:44:04 /

Klíčová slova

HMM-based speech synthesis


 author = {Zden\v{e}k Hanzl\'{i}\v{c}ek},
 title = {Czech HMM-Based Speech Synthesis},
 year = {2010},
 publisher = {Springer Berlin / Heidelberg},
 volume = {6231},
 pages = {291-298},
 booktitle = {Text, Speech and Dialogue},
 series = {Lecture Notes in Computer Science},
 ISBN = {978-3-642-15759-2},
 url = {http://www.kky.zcu.cz/en/publications/ZdenekHanzlicek_2010_CzechHMM-Based},