Bibliografické údaje¶
Název | Czech HMM-Based Speech Synthesis: Experiments with Model Adaptation |
Autor | Hanzlíček, Z. |
Typ publikace | Článek v časopise, odborném periodiku |
Periodikum | Lecture Notes in Computer Science: Text, Speech and Dialogue |
Nakladatel | Springer / Berlin, Heidelberg |
Svazek | LNAI 6836 |
Strana | 107-114 |
Rok | 2011 |
ISBN | 978-3-642-23537-5 |
ISSN | 0302-9743 |
Abstrakt¶
This paper describes some experiments on model adaptation for statistical parametric speech synthesis for the Czech language. For building an experimental TTS system, HTS toolkit was utilised. Speech was represented by using high-quality analysis/synthesis system STRAIGHT. For definition of speech unit context, a new reduced set of contextual factors was proposed. During model clustering, some missing contextual factors, that were not included in this set, can be simulated by using combined context-related clustering questions. The model transformation was performed by a combination of CMLLR and MAP adaptation. Speech data from 3 male and 3 female speakers was used in our experiments. In the performed listening test, speech generated from regularly trained and adapted models was compared. Both voices were evaluated as identical and of a similar quality.